paper-with-me

홈 › Papers

Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method

2026-03-19 · Steffen Dereich, Thang Do, Arnulf Jentzen arxiv

The adaptive moment estimation (Adam) optimizer proposed by Kingma & Ba (2014) is presumably the most popular stochastic gradient descent (SGD) optimization method for the training of deep neural networks (DNNs) in artificial intelligence (AI) systems. Despite its groundbreaking success in the training of AI systems, it still remains an open research problem to provide a complete error analysis of Adam, not only for optimizing DNNs but even when applied to strongly convex stochastic optimization problems (SOPs). Previous error analysis results for strongly convex SOPs in the literature provide conditional convergence analyses that rely on the assumption that Adam does not diverge to infinity but remains uniformly bounded. It is the key contribution of this work to establish uniform a priori bounds for Adam and, thereby, to provide -- for the first time -- an unconditional error analysis for Adam for a large class of strongly convex SOPs.

📄 PDF Abstract BibTeX arXiv:2603.18899

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond

2024-03-22 · Bohan Wang, Huishuai Zhang, Qi Meng, Ruoyu Sun 외

This paper aims to clearly distinguish between Stochastic Gradient Descent with Momentum (SGDM) and Adam in terms of their convergence rates. We demonstrate that Adam achieves a faster convergence compared to SGDM under …

Convergence rates for the RMSprop optimizer with full control of the hyperparameters

2026-08-31 · Steffen Dereich, Arnulf Jentzen arxiv

Popular adaptive stochastic gradient descent (SGD) methods to train artificial intelligence (AI) systems include the RMSprop, the Adam, and the AdamW optimizers, where the adaptivity parts in Adam and AdamW basically jus…

Stochastic Optimization

Provable Quantization with Randomized Hadamard Transform

2026-05-13 · Ying Feng, Piotr Indyk, Michael Kapralov, Dmitry Krachun 외 arxiv

Vector quantization via random projection followed by scalar quantization is a fundamental primitive in machine learning, with applications ranging from similarity search to federated learning and KV cache compression. W…

Federated Learning

Uniform Scaling Limits in AdamW-Trained Transformers

2026-05-11 · William Gibson, Christoph Reisinger arxiv

We study the large-depth limit of transformers trained with AdamW, by modelling the hidden-state dynamics as an interacting particle system (IPS) coupled through the attention mechanism. Under appropriate scaling of the …

MADA: Meta-Adaptive Optimizers through hyper-gradient Descent

2024-01-17 · Kaan Ozkara, Can Karakus, Parameswaran Raman, Mingyi Hong 외

Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this w…